In this paper, we have developed the SEMAR (Smart Environmental Monitoring and Analytics in Real-Time) IoT application server platform for fast deployments of IoT application systems. It provides various integration capabilities for the collection, display, and analysis of sensor data on a single platform. Recently, Artificial Intelligence (AI) has become very popular and widely used in various applications including IoT. To support this growth, the integration of AI into SEMAR is essential to enhance its capabilities after identifying the current trends of applicable AI technologies in IoT applications. In this paper, we first provide a comprehensive review of IoT applications using AI techniques in the literature. They cover predictive analytics, image classification, object detection, text spotting, auditory perception, Natural Language Processing (NLP), and collaborative AI. Next, we identify the characteristics of each technique by considering the key parameters, such as software requirements, input/output (I/O) data types, processing methods, and computations. Third, we design the integration of AI techniques into SEMAR based on the findings. Finally, we discuss use cases of SEMAR for IoT applications with AI techniques. The implementation of the proposed design in SEMAR and its use to IoT applications will be in future works.

The Internet of Things Technology (IoT) is developing so rapidly. One of IoT implementation is an Internet of Underwater Things (IoUT) which is used for underwater monitoring. This paper discuss an integrated smart environment system framework based on IoUT and big data that consist of open platform that processes data from Remotely Operated Vehicle (ROV) and portable sensor with water parameters sensors such an input device to collect and save the data of oxidation-reduction potential, pH, electrical conductivity, total dissolve solid, salinity, dissolved oxygen, and temperature in monitored rivers temporary. Coral Reef Monitoring used for preventing coral bleaching by using underwater camera to take some pictures that will be sent to data center and then analyze it, Wireless Mess Network Access Point used as the way ROVs `talking' to each other while doing a monitoring process in a wide river. Then all of the collected data from ROVs and portable sensor will be saved and analyzed to the data center platform based on Hadoop Multi-Node Cluster. The data will be visualized as a chart or a table and can be accessed world-wide We found that, the processing of the data used in the open platform to be relatively straightforward using a combination of SQL. However, the use of HDFS (Hadoop Distributed File System) as data center and more versatile frameworks such as Mapreduce, Hive, Spark, Redis and more flexible set component of features that particularly facilitate working with larger volumes and more heterogeneous data sources.

Fruit is a commodity highly potential crop in Indonesia. While harvest, fruit production is very abundant. however, the slow harvest process makes the quality decreased. Consequently, the selling price is cheap. In our research, we propose a Deep learning method using faster R-CNN to detect classification a multi-fruits. The input used mango and pitaya fruits. The dataset is a real data taken from a farmer at harvest time and then we into 2 classes, the classification are mango and pitaya for the purpose of training object detection. We used the MobileNet model on TensorFlow platform. In this study, we achieved the accuracy score of about 99%. This method is very appropriate for developed the process of sorting multi-fruits in real-time so as to maintain the quality of the fruit.

The internet of things technology (IoT) is growing very rapidly. IoT implementation has been conducted in several sectors. One of them is for aquaculture. For the traditional farmers, they face problems for monitoring water quality and the way to increase the quality of the water quickly and efficiently. This paper presents a real-time monitoring and controlling system for aquaculture based on If This Then That (IFTTT) model and cloud integration. This system was composed of smart sensor module which supports modularity, smart aeration system for controlling system, local network system, cloud computing system and client visualization data. In order to monitor the water condition, we collect the data from smart sensor module. Smart sensor module consists of sensor dissolved oxygen, potential of hydrogen, water temperature and water level. The components of smart aeration system are microcontroller NodeMCU v3, relay, power supply, and propeller that can produce oxygen. The system could set the IFTTT rules for the ideal water condition for the pond in any kinds of aquaculture based on its needs through the web and android application. The experimental result shows that use IFTTT model makes the aquaculture monitoring system more customizable, expandable and dynamic.

Nowadays, rapid developments of Internet of Things (IoT) technologies have increased possibilities of realizing smart cities where collaborations and integrations of various IoT application systems are essential. However, IoT application systems have often been designed and deployed independently without considering the standards of devices, logics, and data communications. In this paper, we present the design and implementation of the IoT server platform called Smart Environmental Monitoring and Analytical in Real-Time (SEMAR) for integrating IoT application systems using standards. SEMAR offers Big Data environments with built-in functions for data aggregations, synchronizations, and classifications with machine learning. Moreover, plug-in functions can be easily implemented. Data from devices for different sensors can be accepted directly and through network connections, which will be used in real-time for user interfaces, text files, and access to other systems through Representational State Transfer Application Programming Interface (REST API) services. For evaluations of SEMAR, we implemented the platform and integrated five IoT application systems, namely, the air-conditioning guidance system, the fingerprint-based indoor localization system, the water quality monitoring system, the environment monitoring system, and the air quality monitoring system. When compared with existing research on IoT platforms, the proposed SEMAR IoT application server platform offers higher flexibility and interoperability with the functions for IoT device managements, data communications, decision making, synchronizations, and filters that can be easily integrated with external programs or IoT applications without changing the codes. The results confirm the effectiveness and efficiency of the proposal.